EP0552770B1 - Apparatus for extracting facial image characteristic points - Google Patents

Apparatus for extracting facial image characteristic points Download PDF

Info

Publication number
EP0552770B1
EP0552770B1 EP93100900A EP93100900A EP0552770B1 EP 0552770 B1 EP0552770 B1 EP 0552770B1 EP 93100900 A EP93100900 A EP 93100900A EP 93100900 A EP93100900 A EP 93100900A EP 0552770 B1 EP0552770 B1 EP 0552770B1
Authority
EP
European Patent Office
Prior art keywords
shape data
data
face
facial
image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Lifetime
Application number
EP93100900A
Other languages
German (de)
English (en)
French (fr)
Other versions
EP0552770A3 (en
EP0552770A2 (en
Inventor
Yoshiyasu Kado
Masamichi Nakagawa
Fumio Maehara
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Panasonic Holdings Corp
Original Assignee
Matsushita Electric Industrial Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Matsushita Electric Industrial Co Ltd filed Critical Matsushita Electric Industrial Co Ltd
Publication of EP0552770A2 publication Critical patent/EP0552770A2/en
Publication of EP0552770A3 publication Critical patent/EP0552770A3/en
Application granted granted Critical
Publication of EP0552770B1 publication Critical patent/EP0552770B1/en
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T9/00—Image coding
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/117—Identification of persons
    • A61B5/1171—Identification of persons based on the shapes or appearances of their bodies or parts thereof
    • A61B5/1176—Recognition of faces
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/20—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using video object coding

Definitions

  • the present invention relates to a characteristic points extraction part of an individual person identification apparatus and an facial shape characteristics. It is exemplified by a facial expression recognition apparatus for the facial image picture communication.
  • the hue information becomes unstable in such regions that is including sharp edges, making an accurate extraction of the characteristic points impossible.
  • An apparatus for extracting facial image characteristic points based on an image segmentation process including an edge extraction part form performing edge-stressing process on edge parts included in said facial image data to make an edged-image data and a binary level conversion part for performing conversion of the edged-image data into binary-leveled edged-image data on each preestimated region of facial elements is known from "NTZ Archiv vol. 8, no. 9, October 1986, Berlin, DE, Buhr R., pp. 245-256, "Front Face Analysis and Classification (Analyse und Klassification vonhesplainn).
  • an edged image picture is produced by the edge extraction part.
  • the edged image picture includes a large amount of minute noise due to such as moustache or wrinkles. Therefore, for a searching region,i.e., a region to be searched in this image picture, the above-mentioned edged image picture thus obtained by the edge extraction part is converted into a binary-leveled edged image picture by a binary level conversion part. From the searching regions of obtained binary-leveled edged image picture, such a region that is close to the shape data stored in a shape data-base part is selected based on the magnitude of their correspondence factor obtained by an image picture arithmetic processing part.
  • the shape data are updated in a manner that the correspondence factor becomes large in the vicinity of selected region by a shape data updating part. Then, when the correspondence factor outputted from the image picture arithmetic processing part reaches a certain value or more based on those updated shape data, the characteristic points that is the object of the search are outputted from the output part.
  • the apparatus of the present invention owing to the binary level conversion of the edged image picture, is robust against the conditions for taking pictures, such as position of lighting source, color, and others. And since the shape data are stored as the data-base, even for the facial image picture wearing the glasses, for example, erroneous action of the apparatus becomes seldom. Furthermore, owing to the inclusion of the shape data updating part in the apparatus, personal difference depending on individual persons can be absorbed, enabling us to raise the capability of the characteristic points extraction.
  • FIG.1 a constitutional drawing of a first embodiment of the present invention is shown.
  • the output of the image picture input part 1 to which the facial images from a television camera or the likes are inputted is given to an edge extraction part 2, wherein the edge processing is applied to the inputted image picture.
  • the output whereon the edge processing has been applied in the edge extraction part 2 is given to a binary level conversion part 3.
  • binary level conversion process is performed for each preestimated region of respective facial elements.
  • shape data-base part 4 shape data of facial elements such as iris, nose, mouth, and eyebrow are stored.
  • Binary-leveled edged image picture which is processed by the two-level conversion part 3, and the shape data from the shape data-base part 4 are inputted into the image picture arithmetic processing means 5, wherein the correspondence factor therebetween is computed.
  • contents of the shape data-base part 4 is updated in a manner that the corresponding factor increases by the shape data updating part 6.
  • the characteristic points of the image picture are extracted and issued from the output part 7.
  • the facial image picture is taken from the image picture input part 1, and an edged image picture is produced by the edge extraction part 2 from the inputted image picture.
  • computing is made by using an operator such as, for example, the Sobel operator (see, for example, p.98 of D. H. Ballard and C. M. Brown, translated by Akio Soemura "Computer Vision", Japan Computer Association, 1987), wherefrom gradient vectors at respective pixels can be obtained.
  • the gradient vectors thus obtained have their respective magnitudes as well as their directions.
  • the direction of the gradient vector means a direction in which the gradient of brightness of the image picture takes a largest value, and the magnitude thereof means this largest value.
  • they are also called as the edge vectors, since those regions along such the pixels having large gradient vector magnitudes may form edges in the image picture.
  • FIG.2 shows an example of the inputted image picture and the searching regions of respective facial elements.
  • the magnitudes m of edge vectors in a searching region of the iris shown in FIG.2 are converted into binary-leveled values of 0 or 1 using a certain threshold value ⁇ . That is, the raw gradient vectors obtained by applying a gradient operation, such as Sobel operation described above, on the brightness data of respective pixels (or positions), are normalized and converted into either of unit vectors or zero vectors.
  • a gradient operation such as Sobel operation described above
  • sign of these unit vectors obtained as has been described above is reversed (multiplied by -1), and they are called again as the edge vectors (More accurately, they should be called as the normalized edge vector).
  • the above-mentioned threshold value ⁇ must be determined from the frequency distribution of the magnitude m.
  • the threshold value ⁇ is determined in a manner that the binary level conversion is made by setting those data, which fall within 20 % probability of distribution from the largest magnitude in a relevant searching region, to be 1; whereas the rest those data falling within 80 % probability thereof to be 0.
  • FIG.3 shows a shape data of an iris, as an example.
  • the shape data comprise 12 coordinate data and 12 gradient vectors at those respective coordinates.
  • Coordinate data, l k and m k are coordinates at which gradient vectors, v x and v y are given.
  • the gradient vector, v y are unit vectors giving the direction in which largest gradient value is present. Since the iris has a circular shape inside of which is much darker than the outside thereof, coordinate data form a circle and all the gradient vectors given at these coordinates direct to the center of the circle.
  • FIG.4 shows examples of facial elements and their shapes. Facial elements are iris, mouth, nose, eyebrow, and cheek, in this embodiment.
  • the searching region for the edged image picture of iris is scanned and the correspondence factor ⁇ between the inputted observed edge vectors and the gradient vectors of the shape data stored in the data-base is calculated in the arithmetic processing part 5. Since both of the inputted observed data and the shape data stored in the data-base part 4 are given in the form of vector, the correspondence factor ⁇ to be required to calculate can be expressed by the average of inner products between those corresponding two vectors in a manner shown below.
  • the correspondence factor ⁇ for respective coordinates (i,j) in the searching region is calculated.
  • a plural number of coordinates at which values of the correspondence factor ⁇ are large are assigned to be preestimated regions of the relevant facial element.
  • the shape data are updated by the shape data updating part 6, and then the correspondence factor ⁇ is again searched.
  • the scheme of updating is, for example, to move the coordinate of one position of the present data by +1 and then -1 in the direction of the gradient vector and to take either one direction in which the correspondence factor increases.
  • the direction of the gradient vector is also updated in a manner that it coincides with the shape data.
  • all of the elements of shape data are successively updated in a manner that the correspondence factor ⁇ is further improved.
  • the characteristic points are issued from the output part 7.
  • the scheme of this outputting is as follows: For example, when a final values of the correspondence factor ⁇ is less than a certain value t (s>t), regarding the region in which the correspondence factor ⁇ is maximum to be a preestimated region and taking the shape data there to be a facial element to seek, only the necessary characteristic points thereof are issued. And in case that there are a plural number of preestimated regions in which ⁇ is larger than a certain value t, the preestimated region is determined by, for example, a statistical procedure. That is, those regions which are disposed mutually close are all regarded to be genuine shape data. And then, by calculating the average with regard to corresponding positions of all of these shape data, new shape data are obtained.
  • the obtained shape data to be the shape data of a facial element, namely the object to search for
  • only the necessary characteristic points are outputted.
  • the average of coordinates of all the positions of the shape data are calculated to be a center point, and the maximum point and minimum point in the y-coordinate are taken to be the top and the bottom points of the iris, and then resultant data are issued from an output part.
  • the respective characteristic points of mouth, nose, eyebrow, and cheek can be extracted. For example, for the mouth, five points of top, bottom, left, right, and center are extracted; and for eyebrow, four points of top, bottom, left, and right are extracted.
  • the searching region is selected only to the iris region, for example.
  • the searching regions for remaining facial elements are determined by the region determination part 8 based on the extracted characteristic points of the irises.
  • the determination of the searching regions for the remaining facial elements can be processed by utilizing simple common knowledge such that the nose is present between mouth and eyes, and eyebrows are present immediately above eyes.
  • any possible tilt angle of the inputted facial image picture can be obtained.
  • this tilt angle by reversely rotating the shape data stored in the shape data-base part 4 by an amount of this obtained tilt angle by the shape data updating part 6, even from a tilted facial image picture, the extraction of the characteristic points becomes possible.
  • FIG.6 a constitutional drawing of a third embodiment of the present invention is shown.
  • the eyebrow has an edge which is not sharp but gradual. This is because the borders of hair of the eyebrow are gradual. Therefore, differing from-other facial elements, for the eyebrow, it is difficult to obtain strong edge components. Consequently, for the extraction of the characteristic points of the eyebrow, by applying a preprocessing of binary level conversion on the searching regions of eyebrows by a binary level conversion part 11, it becomes possible to obtain strong edge components. This preprocessing is selected by the process selection part 10.
  • the application of the above capability of the present invention is not limited to the eyebrow, but also valid, for example, to such one as moustache wherein its edge component is also gradual. And, in particular, in case of extracting the characteristic points of the eyebrow, since the eyebrow is oblong horizontally, its brightness distribution differs largely between both ends. Consequently, if the searching region is binary-leveled at only one time, it can happen that an accurate shape of eyebrow does not appear. Then, (as in the aspect described in claim 5,) the searching region of the eyebrow is divided into small sub-regions in the vertical direction. In respective small sub-regions, respective threshold values for binary level conversion are respectively determined in a manner that j % probabilities of brightness distribution is set to 0.
  • j is determined in accordance with, for example, the area of respective searching regions.
  • respective regions can be binary-leveled individually.
  • the threshold value deviates largely from the average value, it is regarded to be either one of
  • the best fit preestimated regions are searched for respective facial elements. And then for respective preestimated regions, the characteristic points which are the object of search can be obtained based on the shape data.
  • FIG.8 an example of hardware configuration of computer for use in the present invention is shown in FIG.8, and an example of the procedure of extraction of the facial image characteristic points, which has been already described in the above embodiments, is now explained using a flow chart shown in FIG.9(a) and FIG.9(b).
  • FIG.8 shows a circuit block diagram giving a fundamental hardware configuration of the apparatus of the present invention.
  • the facial image picture is taken into the apparatus through a television camera 101.
  • the facial image picture signal issued from the television camera 101 is inputted into an A/D converter 102.
  • a central processing unit, CPU 103 executes all the required functions, such as data access, transfer, store, arithmetic processing, and other functions for data under instructions of program installed in the apparatus. Functions or parts represented by boxes in FIG.5 through FIG.7 are preferably executed by such the installed program.
  • Numeral 104 designates an image picture memory.
  • the output of the A/D converter is memorized through a CPU 103 in an input image picture memory 104A as the input image picture data for all of each pixel.
  • the input image picture data are converted into edged image picture data and further converted binary-leveled edged image picture data through the CPU 103. They are stored in an edged image picture memory 104B and a binary-leveled edged image picture memory 104C, respectively.
  • Numeral 105 is a memory for storing the shape data-base of facial elements such as eyes, mouth, eyebrow, or cheek. data-base of each facial element includes three different sizes of small, medium and large.
  • the correspondence factor between the binary-leveled edged image picture data and the shape data stored in the shape data-base memory 105 is computed; and the shape data are updated in a manner that the correspondence factor increases by the CPU 103.
  • Numeral 106 is a working area of memory used for temporary purpose of the processing.
  • Numeral 107 is an output area of memory for storing the extracted facial image characteristic points of necessary facial elements.
  • FIG.9(a) and FIG.9(b) in combination, a flow chart of an example of the procedure of extraction of the facial image characteristic points is shown.
  • a flow starting at a start 201 through a step 216 corresponds to the process for the extraction of facial image characteristic points of eyes
  • flow of a step 302 through a step 316 corresponds to the process for the extraction of facial image characteristic points of mouth.
  • almost the same flow chart as for the above two facial elements can be applied.
  • the present invention it is unnecessary to use any color picture image, and thereby the extraction of the characteristic points is possible even from a monochromatic photograph.
  • the shape data by preparing a plural number of data for one facial element, the obtainable accuracy of extraction of the characteristic points can be improved.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Pathology (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Human Computer Interaction (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
  • Collating Specific Patterns (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
EP93100900A 1992-01-23 1993-01-21 Apparatus for extracting facial image characteristic points Expired - Lifetime EP0552770B1 (en)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
JP9753/92 1992-01-23
JP975392 1992-01-23
JP4009753A JP2973676B2 (ja) 1992-01-23 1992-01-23 顔画像特徴点抽出装置

Publications (3)

Publication Number Publication Date
EP0552770A2 EP0552770A2 (en) 1993-07-28
EP0552770A3 EP0552770A3 (en) 1994-06-15
EP0552770B1 true EP0552770B1 (en) 2003-07-16

Family

ID=11729055

Family Applications (1)

Application Number Title Priority Date Filing Date
EP93100900A Expired - Lifetime EP0552770B1 (en) 1992-01-23 1993-01-21 Apparatus for extracting facial image characteristic points

Country Status (5)

Country Link
US (1) US5905807A (ja)
EP (1) EP0552770B1 (ja)
JP (1) JP2973676B2 (ja)
KR (1) KR0130962B1 (ja)
DE (1) DE69333094T2 (ja)

Families Citing this family (126)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5995639A (en) * 1993-03-29 1999-11-30 Matsushita Electric Industrial Co., Ltd. Apparatus for identifying person
US5512939A (en) * 1994-04-06 1996-04-30 At&T Corp. Low bit rate audio-visual communication system having integrated perceptual speech and video coding
DE69636695T2 (de) * 1995-02-02 2007-03-01 Matsushita Electric Industrial Co., Ltd., Kadoma Bildverarbeitungsvorrichtung
JP3426060B2 (ja) * 1995-07-28 2003-07-14 三菱電機株式会社 顔画像処理装置
JP3529954B2 (ja) * 1996-09-05 2004-05-24 株式会社資生堂 顔だち分類法及び顔だちマップ
US6184926B1 (en) * 1996-11-26 2001-02-06 Ncr Corporation System and method for detecting a human face in uncontrolled environments
US6202151B1 (en) * 1997-05-09 2001-03-13 Gte Service Corporation System and method for authenticating electronic transactions using biometric certificates
US6105010A (en) * 1997-05-09 2000-08-15 Gte Service Corporation Biometric certifying authorities
US5892837A (en) * 1997-08-29 1999-04-06 Eastman Kodak Company Computer program product for locating objects in an image
US6108437A (en) * 1997-11-14 2000-08-22 Seiko Epson Corporation Face recognition apparatus, method, system and computer readable medium thereof
AU1613599A (en) 1997-12-01 1999-06-16 Arsev H. Eraslan Three-dimensional face identification system
BR9906453A (pt) * 1998-05-19 2000-09-19 Sony Computer Entertainment Inc Dispositivo e método do processamento de imagem, e meio de distribuição.
JP2000048036A (ja) * 1998-07-28 2000-02-18 Canon Inc 画像処理装置およびその方法
US6606398B2 (en) * 1998-09-30 2003-08-12 Intel Corporation Automatic cataloging of people in digital photographs
JP2000165648A (ja) * 1998-11-27 2000-06-16 Fuji Photo Film Co Ltd 画像処理方法および装置並びに記録媒体
US6263113B1 (en) * 1998-12-11 2001-07-17 Philips Electronics North America Corp. Method for detecting a face in a digital image
US6507660B1 (en) * 1999-05-27 2003-01-14 The United States Of America As Represented By The Secretary Of The Navy Method for enhancing air-to-ground target detection, acquisition and terminal guidance and an image correlation system
JP2000350123A (ja) 1999-06-04 2000-12-15 Fuji Photo Film Co Ltd 画像選択装置、カメラ、画像選択方法及び記録媒体
US7474787B2 (en) * 1999-12-28 2009-01-06 Minolta Co., Ltd. Apparatus and method of detecting specified pattern
EP1290571A4 (en) * 2000-04-17 2005-11-02 Igt Reno Nev SYSTEM AND METHOD FOR DETECTING THE PICTURE OF A PLAYER TO INTEGRATE IT INTO A GAME
KR20000054824A (ko) * 2000-06-27 2000-09-05 이성환 얼굴 영상을 이용한 이상형 검색 시스템 및 그 제어 방법
JP4469476B2 (ja) 2000-08-09 2010-05-26 パナソニック株式会社 眼位置検出方法および眼位置検出装置
AU2001282483A1 (en) * 2000-08-29 2002-03-13 Imageid Ltd. Indexing, storage and retrieval of digital images
DE10043460C2 (de) * 2000-09-04 2003-01-30 Fraunhofer Ges Forschung Auffinden von Körperpartien durch Auswerten von Kantenrichtungsinformation
US6920237B2 (en) * 2000-12-19 2005-07-19 Eastman Kodak Company Digital image processing method and computer program product for detecting human irises in an image
JP3846851B2 (ja) * 2001-02-01 2006-11-15 松下電器産業株式会社 画像のマッチング処理方法及びその装置
DE60213032T2 (de) * 2001-05-22 2006-12-28 Matsushita Electric Industrial Co. Ltd. Gerät zur Gesichtsdetektion, Gerät zur Detektion der Gesichtspose, Gerät zur Extraktion von Teilbildern und Verfahren für diese Geräte
US7136513B2 (en) * 2001-11-08 2006-11-14 Pelco Security identification system
US7305108B2 (en) * 2001-11-08 2007-12-04 Pelco Security identification system
US7239726B2 (en) * 2001-12-12 2007-07-03 Sony Corporation System and method for effectively extracting facial feature information
US20030174869A1 (en) * 2002-03-12 2003-09-18 Suarez Anthony P. Image processing apparatus, image processing method, program and recording medium
WO2004040531A1 (en) * 2002-10-28 2004-05-13 Morris Steffin Method and apparatus for detection of drownsiness and for monitoring biological processes
US7577297B2 (en) 2002-12-16 2009-08-18 Canon Kabushiki Kaisha Pattern identification method, device thereof, and program thereof
US7471846B2 (en) 2003-06-26 2008-12-30 Fotonation Vision Limited Perfecting the effect of flash within an image acquisition devices using face detection
US7620218B2 (en) * 2006-08-11 2009-11-17 Fotonation Ireland Limited Real-time face tracking with reference images
US8896725B2 (en) 2007-06-21 2014-11-25 Fotonation Limited Image capture device with contemporaneous reference image capture mechanism
US7574016B2 (en) 2003-06-26 2009-08-11 Fotonation Vision Limited Digital image processing using face detection information
US8682097B2 (en) 2006-02-14 2014-03-25 DigitalOptics Corporation Europe Limited Digital image enhancement with reference images
US8498452B2 (en) 2003-06-26 2013-07-30 DigitalOptics Corporation Europe Limited Digital image processing using face detection information
US7792970B2 (en) 2005-06-17 2010-09-07 Fotonation Vision Limited Method for establishing a paired connection between media devices
US9692964B2 (en) 2003-06-26 2017-06-27 Fotonation Limited Modification of post-viewing parameters for digital images using image region or feature information
US7844076B2 (en) 2003-06-26 2010-11-30 Fotonation Vision Limited Digital image processing using face detection and skin tone information
US7440593B1 (en) 2003-06-26 2008-10-21 Fotonation Vision Limited Method of improving orientation and color balance of digital images using face detection information
US9129381B2 (en) 2003-06-26 2015-09-08 Fotonation Limited Modification of post-viewing parameters for digital images using image region or feature information
US7269292B2 (en) 2003-06-26 2007-09-11 Fotonation Vision Limited Digital image adjustable compression and resolution using face detection information
US7616233B2 (en) 2003-06-26 2009-11-10 Fotonation Vision Limited Perfecting of digital image capture parameters within acquisition devices using face detection
US8989453B2 (en) 2003-06-26 2015-03-24 Fotonation Limited Digital image processing using face detection information
US8494286B2 (en) 2008-02-05 2013-07-23 DigitalOptics Corporation Europe Limited Face detection in mid-shot digital images
US7565030B2 (en) * 2003-06-26 2009-07-21 Fotonation Vision Limited Detecting orientation of digital images using face detection information
US8593542B2 (en) 2005-12-27 2013-11-26 DigitalOptics Corporation Europe Limited Foreground/background separation using reference images
US8330831B2 (en) 2003-08-05 2012-12-11 DigitalOptics Corporation Europe Limited Method of gathering visual meta data using a reference image
US8948468B2 (en) 2003-06-26 2015-02-03 Fotonation Limited Modification of viewing parameters for digital images using face detection information
US8155397B2 (en) 2007-09-26 2012-04-10 DigitalOptics Corporation Europe Limited Face tracking in a camera processor
EP3358501B1 (en) 2003-07-18 2020-01-01 Canon Kabushiki Kaisha Image processing device, imaging device, image processing method
US7920725B2 (en) * 2003-09-09 2011-04-05 Fujifilm Corporation Apparatus, method, and program for discriminating subjects
JP4569471B2 (ja) * 2003-09-26 2010-10-27 株式会社ニコン 電子画像蓄積方法、電子画像蓄積装置、及び電子画像蓄積システム
JP2005190400A (ja) * 2003-12-26 2005-07-14 Seiko Epson Corp 顔画像検出方法及び顔画像検出システム並びに顔画像検出プログラム
JP4317465B2 (ja) * 2004-02-13 2009-08-19 本田技研工業株式会社 顔識別装置、顔識別方法及び顔識別プログラム
JP4257250B2 (ja) * 2004-03-30 2009-04-22 富士通株式会社 生体情報照合装置並びに生体特徴情報絞込み装置，生体特徴情報絞込みプログラムおよび同プログラムを記録したコンピュータ読取可能な記録媒体
JP4683200B2 (ja) * 2004-04-30 2011-05-11 花王株式会社 髪領域の自動抽出方法
JP2005346806A (ja) * 2004-06-02 2005-12-15 Funai Electric Co Ltd Ｄｖｄレコーダおよび記録再生装置
US7660482B2 (en) * 2004-06-23 2010-02-09 Seiko Epson Corporation Method and apparatus for converting a photo to a caricature image
US8320641B2 (en) 2004-10-28 2012-11-27 DigitalOptics Corporation Europe Limited Method and apparatus for red-eye detection using preview or other reference images
US8503800B2 (en) 2007-03-05 2013-08-06 DigitalOptics Corporation Europe Limited Illumination detection using classifier chains
US7315631B1 (en) 2006-08-11 2008-01-01 Fotonation Vision Limited Real-time face tracking in a digital image acquisition device
JP2006287917A (ja) * 2005-03-08 2006-10-19 Fuji Photo Film Co Ltd 画像出力装置、画像出力方法、および画像出力プログラム
US20080175513A1 (en) * 2005-04-19 2008-07-24 Ming-Jun Lai Image Edge Detection Systems and Methods
CN1879553B (zh) * 2005-06-15 2010-10-06 佳能株式会社 在胸部图像中检测边界的方法及装置
US7817826B2 (en) * 2005-08-12 2010-10-19 Intelitrac Inc. Apparatus and method for partial component facial recognition
JP4414401B2 (ja) 2006-02-10 2010-02-10 富士フイルム株式会社 顔特徴点検出方法および装置並びにプログラム
JP5354842B2 (ja) 2006-05-26 2013-11-27 キヤノン株式会社 画像処理方法および画像処理装置
EP2033142B1 (en) 2006-06-12 2011-01-26 Tessera Technologies Ireland Limited Advances in extending the aam techniques from grayscale to color images
US7403643B2 (en) 2006-08-11 2008-07-22 Fotonation Vision Limited Real-time face tracking in a digital image acquisition device
US7916897B2 (en) 2006-08-11 2011-03-29 Tessera Technologies Ireland Limited Face tracking for controlling imaging parameters
DE102006045828B4 (de) * 2006-09-22 2010-06-24 Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. Verfahren und Vorrichtung zum Erkennen eines Gesichts sowie ein Gesichtserkennungsmodul
US8055067B2 (en) 2007-01-18 2011-11-08 DigitalOptics Corporation Europe Limited Color segmentation
DE602008001607D1 (de) 2007-02-28 2010-08-05 Fotonation Vision Ltd Trennung der direktionalen beleuchtungsvariabilität in der statistischen gesichtsmodellierung auf basis von texturraumzerlegungen
US8649604B2 (en) 2007-03-05 2014-02-11 DigitalOptics Corporation Europe Limited Face searching and detection in a digital image acquisition device
JP4928346B2 (ja) 2007-05-08 2012-05-09 キヤノン株式会社 画像検索装置および画像検索方法ならびにそのプログラムおよび記憶媒体
US7916971B2 (en) * 2007-05-24 2011-03-29 Tessera Technologies Ireland Limited Image processing method and apparatus
US7855737B2 (en) 2008-03-26 2010-12-21 Fotonation Ireland Limited Method of making a digital camera image of a scene including the camera user
JP5127592B2 (ja) 2008-06-25 2013-01-23 キヤノン株式会社 画像処理装置および画像処理方法、プログラム並びに、コンピュータ読み取り可能な記録媒体
JP5132445B2 (ja) 2008-06-25 2013-01-30 キヤノン株式会社 画像処理装置および画像処理方法並びにコンピュータプログラムおよび記憶媒体
JP5547730B2 (ja) 2008-07-30 2014-07-16 デジタルオプティックス・コーポレイション・ヨーロッパ・リミテッド 顔検知を用いた顔及び肌の自動美化
US8379917B2 (en) 2009-10-02 2013-02-19 DigitalOptics Corporation Europe Limited Face recognition performance using additional image features
US8523570B2 (en) * 2010-05-21 2013-09-03 Photometria, Inc System and method for providing a face chart
US8550818B2 (en) * 2010-05-21 2013-10-08 Photometria, Inc. System and method for providing and modifying a personalized face chart
JP5719123B2 (ja) 2010-05-24 2015-05-13 キヤノン株式会社 画像処理装置、画像処理方法、およびプログラム
JP5744429B2 (ja) 2010-07-16 2015-07-08 キヤノン株式会社 画像処理装置、画像処理方法、およびプログラム
JP5744431B2 (ja) 2010-07-16 2015-07-08 キヤノン株式会社 画像処理装置、画像処理方法、プログラム
JP5744430B2 (ja) 2010-07-16 2015-07-08 キヤノン株式会社 画像処理装置、画像処理方法、プログラム
JP5733032B2 (ja) * 2011-06-06 2015-06-10 ソニー株式会社 画像処理装置および方法、画像処理システム、プログラム、および、記録媒体
US8634648B2 (en) * 2011-12-07 2014-01-21 Elwha Llc Reporting informational data indicative of a possible non-imaged portion of a skin
JP6074182B2 (ja) 2012-07-09 2017-02-01 キヤノン株式会社 画像処理装置及び画像処理方法、プログラム
JP5956860B2 (ja) 2012-07-09 2016-07-27 キヤノン株式会社 画像処理装置、画像処理方法、プログラム
JP6071289B2 (ja) 2012-07-09 2017-02-01 キヤノン株式会社 画像処理装置、画像処理方法、およびプログラム
JP6222900B2 (ja) 2012-07-09 2017-11-01 キヤノン株式会社 画像処理装置、画像処理方法およびプログラム
JP5981789B2 (ja) 2012-07-09 2016-08-31 キヤノン株式会社 画像処理装置、画像処理方法およびプログラム
JP6045232B2 (ja) 2012-07-09 2016-12-14 キヤノン株式会社 画像処理装置、画像処理方法、及びプログラム
JP6071288B2 (ja) 2012-07-09 2017-02-01 キヤノン株式会社 画像処理装置、画像処理方法、及びプログラム
JP6012308B2 (ja) 2012-07-09 2016-10-25 キヤノン株式会社 画像処理装置、画像処理方法、及びプログラム
JP6039942B2 (ja) 2012-07-09 2016-12-07 キヤノン株式会社 情報処理装置及びその制御方法及びプログラム
JP6016489B2 (ja) 2012-07-09 2016-10-26 キヤノン株式会社 画像処理装置、画像処理装置の制御方法、プログラム
JP6012310B2 (ja) 2012-07-09 2016-10-25 キヤノン株式会社 画像処理装置、画像処理方法、およびプログラム
JP6012309B2 (ja) 2012-07-09 2016-10-25 キヤノン株式会社 情報処理装置、情報処理方法、およびプログラム
JP5993642B2 (ja) 2012-07-09 2016-09-14 キヤノン株式会社 情報処理装置及びその制御方法及びプログラム
JP6071287B2 (ja) 2012-07-09 2017-02-01 キヤノン株式会社 画像処理装置、画像処理方法、及びプログラム
KR102094723B1 (ko) * 2012-07-17 2020-04-14 삼성전자주식회사 견고한 얼굴 표정 인식을 위한 특징 기술자
US9600711B2 (en) * 2012-08-29 2017-03-21 Conduent Business Services, Llc Method and system for automatically recognizing facial expressions via algorithmic periocular localization
KR102013928B1 (ko) 2012-12-28 2019-08-23 삼성전자주식회사 영상 변형 장치 및 그 방법
JP6261206B2 (ja) 2013-06-28 2018-01-17 キヤノン株式会社 情報処理装置、情報処理方法及びプログラム
JP6167733B2 (ja) 2013-07-30 2017-07-26 富士通株式会社 生体特徴ベクトル抽出装置、生体特徴ベクトル抽出方法、および生体特徴ベクトル抽出プログラム
WO2015029392A1 (ja) 2013-08-30 2015-03-05 パナソニックＩｐマネジメント株式会社 メイクアップ支援装置、メイクアップ支援方法、およびメイクアップ支援プログラム
JP6282065B2 (ja) 2013-09-05 2018-02-21 キヤノン株式会社 画像処理装置、画像処理方法、及びプログラム
JP2015053541A (ja) 2013-09-05 2015-03-19 キヤノン株式会社 画像処理装置、画像処理方法、及びプログラム
JP6168928B2 (ja) 2013-09-05 2017-07-26 キヤノン株式会社 画像処理装置、画像処理方法およびプログラム
US9501689B2 (en) * 2014-03-13 2016-11-22 Panasonic Intellectual Property Management Co., Ltd. Image processing apparatus and image processing method
CN104091148B (zh) * 2014-06-16 2017-06-27 联想(北京)有限公司 一种人脸特征点定位方法和装置
US9384385B2 (en) 2014-11-06 2016-07-05 Intel Corporation Face recognition using gradient based feature analysis
US9986289B2 (en) 2015-03-02 2018-05-29 The Nielsen Company (Us), Llc Methods and apparatus to count people
US9881205B2 (en) 2015-05-29 2018-01-30 Aware, Inc. Facial identification techniques
JP6664163B2 (ja) * 2015-08-05 2020-03-13 キヤノン株式会社 画像識別方法、画像識別装置及びプログラム
US9984282B2 (en) * 2015-12-10 2018-05-29 Perfect Corp. Systems and methods for distinguishing facial features for cosmetic application
CN107038401B (zh) * 2016-02-03 2018-10-30 北方工业大学 一种嘴唇轮廓的分割及特征提取方法
KR102555096B1 (ko) * 2016-06-09 2023-07-13 엘지디스플레이 주식회사 데이터 압축 방법 및 이를 이용한 유기 발광 다이오드 표시 장치
US11048921B2 (en) 2018-05-09 2021-06-29 Nviso Sa Image processing system for extracting a behavioral profile from images of an individual specific to an event

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3648240A (en) * 1970-01-15 1972-03-07 Identification Corp Personnel identification apparatus
SE365325B (ja) * 1971-11-04 1974-03-18 Rothfjell R
SE382704B (sv) * 1974-06-14 1976-02-09 Rothfjell Rolf Eric Forfarande for framtagning av karakteristiska konturer ur en fergbild.
WO1985004088A1 (en) * 1984-03-20 1985-09-26 Joseph Rice Method and apparatus for the identification of individuals
JPS62502575A (ja) * 1985-04-22 1987-10-01 ザ　クワンタン　フアンド　リミテイド 皮膚の模様を確認する方法及び装置
US4724542A (en) * 1986-01-22 1988-02-09 International Business Machines Corporation Automatic reference adaptation during dynamic signature verification
JPH01158579A (ja) * 1987-09-09 1989-06-21 Aisin Seiki Co Ltd 像認識装置
US4975969A (en) * 1987-10-22 1990-12-04 Peter Tal Method and apparatus for uniquely identifying individuals by particular physical characteristics and security system utilizing the same
US5012522A (en) * 1988-12-08 1991-04-30 The United States Of America As Represented By The Secretary Of The Air Force Autonomous face recognition machine
US5231674A (en) * 1989-06-09 1993-07-27 Lc Technologies, Inc. Eye tracking method and apparatus
US5210797A (en) * 1989-10-30 1993-05-11 Kokusan Kinzoku Kogyo Kabushiki Kaisha Adaptive dictionary for a fingerprint recognizer
US4993068A (en) * 1989-11-27 1991-02-12 Motorola, Inc. Unforgeable personal identification system
US5164992A (en) * 1990-11-01 1992-11-17 Massachusetts Institute Of Technology Face recognition system
US5163094A (en) * 1991-03-20 1992-11-10 Francine J. Prokoski Method for identifying individuals from analysis of elemental shapes derived from biosensor data

Also Published As

Publication number Publication date
JPH05197793A (ja) 1993-08-06
DE69333094D1 (de) 2003-08-21
EP0552770A3 (en) 1994-06-15
DE69333094T2 (de) 2004-06-03
US5905807A (en) 1999-05-18
JP2973676B2 (ja) 1999-11-08
KR930016911A (ko) 1993-08-30
KR0130962B1 (ko) 1998-04-24
EP0552770A2 (en) 1993-07-28

Similar Documents

Publication Publication Date Title
EP0552770B1 (en) Apparatus for extracting facial image characteristic points
US7035461B2 (en) Method for detecting objects in digital images
US5450504A (en) Method for finding a most likely matching of a target facial image in a data base of facial images
Sun et al. Face detection based on color and local symmetry information
US7460693B2 (en) Method and apparatus for the automatic detection of facial features
AU2005278003B8 (en) Single image based multi-biometric system and method
US5715325A (en) Apparatus and method for detecting a face in a video image
US5805745A (en) Method for locating a subject's lips in a facial image
EP0899680B1 (en) Method for automatic detection of human eyes in digital images
KR100730500B1 (ko) 화상 처리 장치와 화상 처리 방법 및 기록 매체
Herodotou et al. Automatic location and tracking of the facial region in color video sequences
He et al. Real-time human face detection in color image
US20080298645A1 (en) Personal authentication apparatus and personal authentication method
WO2005024708A1 (en) The pupil detection method and shape descriptor extraction method for a iris recognition, iris feature extraction apparatus and method, and iris recognition system and method using its
KR20010103631A (ko) 생물 측정학-기반 얼굴 특징 추출을 위한 시스템 및 방법
KR20090087895A (ko) 생체인식정보의 추출과 대조를 위한 방법 및 장치
EP0471472B1 (en) Image processing method and apparatus therefor
JPH11110542A (ja) パターン抽出方法および装置、そのプログラムを記録した媒体
Kosugi Human‐face search and location in a scene by multi‐pyramid architecture for personal identification
US20030059117A1 (en) Systems and methods for image processing, and recording medium therefor
Milgram et al. Multi-stage combination of geometric and colorimetric detectors for eyes localization
JP3841482B2 (ja) 顔画像認識装置
Mannaert et al. Self-organizing system for analysis and identification of human faces
KR20020092522A (ko) 손가락 마디 지문을 이용한 개인 식별 방법 및 그 장치
Kosugi et al. Person identification system based on a trapezoid pyramid architecture of a gray-level image

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 19930121

AK Designated contracting states

Kind code of ref document: A2

Designated state(s): DE FR GB

PUAL Search report despatched

Free format text: ORIGINAL CODE: 0009013

AK Designated contracting states

Kind code of ref document: A3

Designated state(s): DE FR GB

17Q First examination report despatched

Effective date: 19980917

GRAH Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOS IGRA

GRAH Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOS IGRA

GRAH Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOS IGRA

GRAH Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOS IGRA

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

AK Designated contracting states

Designated state(s): DE FR GB

REG Reference to a national code

Ref country code: GB

Ref legal event code: FG4D

REF Corresponds to:

Ref document number: 69333094

Country of ref document: DE

Date of ref document: 20030821

Kind code of ref document: P

ET Fr: translation filed
PLBE No opposition filed within time limit

Free format text: ORIGINAL CODE: 0009261

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT

26N No opposition filed

Effective date: 20040419

REG Reference to a national code

Ref country code: DE

Ref legal event code: R084

Ref document number: 69333094

Country of ref document: DE

Effective date: 20111010

Ref country code: DE

Ref legal event code: R084

Ref document number: 69333094

Country of ref document: DE

Effective date: 20111201

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: FR

Payment date: 20120202

Year of fee payment: 20

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: DE

Payment date: 20120118

Year of fee payment: 20

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: GB

Payment date: 20120118

Year of fee payment: 20

REG Reference to a national code

Ref country code: DE

Ref legal event code: R071

Ref document number: 69333094

Country of ref document: DE

REG Reference to a national code

Ref country code: GB

Ref legal event code: PE20

Expiry date: 20130120

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: DE

Free format text: LAPSE BECAUSE OF EXPIRATION OF PROTECTION

Effective date: 20130122

Ref country code: GB

Free format text: LAPSE BECAUSE OF EXPIRATION OF PROTECTION

Effective date: 20130120